at://
/
app.bsky.feed.post
/
3mkzsnzi6vt22
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Results: FINER-Tuning improves performance on our FINER benchmarks, transfers to other hallucination benchmarks, and even boosts general MLLM ability. On InternVL3.5-14B, we get up to +24.2% on FINER without hurting overall capability.
1mo
ExplainableML
